INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reviewer

-0.88

 kindred

-0.68

 DEFENSE

-0.68

 ounce

-0.67

packing

-0.66

 concealed

-0.66

 salute

-0.65

 unex

-0.65

 athlet

-0.65

 comrade

-0.64

POSITIVE LOGITS

zos

0.89

otten

0.79

NetMessage

0.76

henko

0.69

lins

0.69

zar

0.68

Roberts

0.68

lp

0.68

TED

0.67

Rich

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.